Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0712. Min Act: -0.1700
Data Index: 5811957 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0712. Min Act: -0.1700
Data Index: 3409573 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0397. Min Act: -0.1700
Data Index: 1149768 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0239. Min Act: -0.1700
Data Index: 1549765 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0081. Min Act: -0.1700
Data Index: 4331905 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0712. Min Range: -3.0712
Max Act: 3.0239. Min Act: -0.1700
Data Index: 1765417 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9765. Min Act: -0.1700
Data Index: 3405403 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9448. Min Act: -0.1700
Data Index: 4333706 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9448. Min Act: -0.1700
Data Index: 4318260 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9448. Min Act: -0.1700
Data Index: 7891361 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9290. Min Act: -0.1700
Data Index: 2411297 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9448. Min Act: -0.1700
Data Index: 8504727 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9290. Min Act: -0.1700
Data Index: 2352900 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9132. Min Act: -0.1700
Data Index: 109038 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9448. Min Act: -0.1700
Data Index: 2686966 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9290. Min Act: -0.1700
Data Index: 109044 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9290. Min Act: -0.1700
Data Index: 1762795 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9132. Min Act: -0.1700
Data Index: 5991769 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9132. Min Act: -0.1700
Data Index: 2844521 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0712. Min Range: -3.0712
Max Act: 2.9132. Min Act: -0.1700
Data Index: 4608209 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19